2 papers
cs.CV2026
Diffusion Mental Averages
Phonphrm Thawatdamrongkit, Sukit Seripanitkarn, Supasorn Suwajanakorn
Can a diffusion model produce its own "mental average" of a concept-one that is as sharp and realistic as a typical sample? We introduce Diffusion Mental Averages (DMA), a model-ce…
cs.CV2025
Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality
Pramook Khungurn, Sukit Seripanitkarn, Phonphrm Thawatdamrongkit +1
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear- noise schedule that spends much of its sampling steps at high nois…